Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 442 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5068. Min Range: -1.5068

Max Act: 1.5068. Min Act: -0.0000

Data Index: 532105 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 1.5068. Min Range: -1.5068

Max Act: 1.2948. Min Act: -0.0000

Data Index: 964093 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 1.5068. Min Range: -1.5068

Max Act: 1.2714. Min Act: -0.0000

Data Index: 988729 (C4 (Web Text))

Max Activating Token Index: 536

Text #3

Max Range: 1.5068. Min Range: -1.5068

Max Act: 1.2293. Min Act: -0.0000

Data Index: 1318176 (C4 (Web Text))

Max Activating Token Index: 481

Text #4

Max Range: 1.5068. Min Range: -1.5068

Max Act: 1.2008. Min Act: -0.0000

Data Index: 1008289 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 1.5068. Min Range: -1.5068

Max Act: 1.1283. Min Act: -0.0000

Data Index: 898239 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 1.5068. Min Range: -1.5068

Max Act: 1.1137. Min Act: -0.0000

Data Index: 1353496 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 1.5068. Min Range: -1.5068

Max Act: 1.0823. Min Act: -0.0000

Data Index: 119360 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 1.5068. Min Range: -1.5068

Max Act: 1.1152. Min Act: -0.0000

Data Index: 413087 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 1.5068. Min Range: -1.5068

Max Act: 1.0615. Min Act: -0.0000

Data Index: 398768 (C4 (Web Text))

Max Activating Token Index: 530

Text #10

Max Range: 1.5068. Min Range: -1.5068

Max Act: 1.0445. Min Act: -0.0000

Data Index: 224184 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 1.5068. Min Range: -1.5068

Max Act: 1.0335. Min Act: -0.0000

Data Index: 235766 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 1.5068. Min Range: -1.5068

Max Act: 1.0811. Min Act: -0.0000

Data Index: 1133880 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 1.5068. Min Range: -1.5068

Max Act: 1.0046. Min Act: -0.0000

Data Index: 121168 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 1.5068. Min Range: -1.5068

Max Act: 0.9397. Min Act: -0.0000

Data Index: 1216230 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 1.5068. Min Range: -1.5068

Max Act: 0.9958. Min Act: -0.0000

Data Index: 521417 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 1.5068. Min Range: -1.5068

Max Act: 0.9044. Min Act: -0.0000

Data Index: 552178 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 1.5068. Min Range: -1.5068

Max Act: 0.9443. Min Act: 0.0000

Data Index: 302880 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 1.5068. Min Range: -1.5068

Max Act: 0.9923. Min Act: -0.0000

Data Index: 100643 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 1.5068. Min Range: -1.5068

Max Act: 0.9218. Min Act: -0.0000

Data Index: 455129 (C4 (Web Text))

Max Activating Token Index: 590